© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 22-LLAMASCOPE-RES-32K
    11. 16582
    Prev
    Next
    INDEX
    Explanations

    references to metal and metallic materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    es
    -0.18
    ester
    -0.18
    edar
    -0.17
    estro
    -0.17
    ety
    -0.17
    ez
    -0.16
    esi
    -0.16
    ÏĨή
    -0.15
    eyim
    -0.15
    ÙĨ
    -0.15
    POSITIVE LOGITS
    licity
    0.39
    lica
    0.36
    lic
    0.32
    anguage
    0.30
    lico
    0.27
    working
    0.26
    urgical
    0.26
    urgy
    0.25
    workers
    0.24
    lo
    0.24
    Activations Density 0.012%

    No Known Activations